Research Article
An Activity-Based Travel Personalization Tool Driven by the Genetic Algorithm
Table 4
The results of user B’s daily activity chain optimization.
| User B | The best-fit solution offered | The best-fit solution with the alternative mode | PT + walking | Cycling | The IDs of the activities in an order | Start time | End time | The IDs of the activities in an order | Start time | End time |
| 0 M | | 08:00 | 0 | | 08:00 | 6 M | 08:03 | 08:23 | 6 | 08:05 | 08:25 | 1 M | 09:00 | 14:00 | 1 | 09:00 | 14:00 | 2 W | 14:30 | 15:15 | 2 | 14:30 | 15:15 | 4 W | 15:16 | 15:46 | 4 | 15:17 | 15:47 | 5 M | 15:46 | 16:06 | 3 | 15:47 | 16:17 | 3 W | 16:08 | 16:38 | 5 | 16:19 | 16:39 | 7 | 16:39 | | 7 | 16:43 | |
| Total absolute travel time: 23.3 minutes | Total absolute travel time: 34.6 minutes | Estimated congestion delay 0 minute | Estimated congestion delay: 0 minute | Estimated out-vehicle time: 20 minutes | Estimated out-vehicle time: 0 minute | Utility score: 868.7 | Utility score: 195.8 |
|
|
M = metro, T = tram, W = walking; = flexible location priority. |